We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Assessment of Machine Learning vs Standard Prediction Rules for Predicting Hospital Readmissions.
- Authors
Morgan, Daniel J.; Bame, Bill; Zimand, Paul; Dooley, Patrick; Thom, Kerri A.; Harris, Anthony D.; Bentzen, Soren; Ettinger, Walt; Garrett-Ray, Stacy D.; Tracy, J. Kathleen; Liang, Yuanyuan
- Abstract
This prognostic study compares standard readmission risk assessment scores with a machine learning score, the Baltimore score, for predicting 30-day unplanned hospital readmissions calculated in real time. Key Points: Question: Does a machine learning score better predict hospital readmissions than standard readmission scores? Findings: In this prognostic study including 14 062 individual patients and 16 649 discharges from 3 hospitals, a machine learning score (the Baltimore score) was better able to predict hospital readmissions compared with standard readmission scores. Area under the receiver operating characteristic curve for the Baltimore score at discharge was 25.5% to 54.9% more efficient compared with commonly used scores with the difference between scores being statistically significant. Meaning: The findings suggest that an individual hospital-tailored, machine learning–based score better predicts readmissions compared with standard methods. Importance: Hospital readmissions are associated with patient harm and expense. Ways to prevent hospital readmissions have focused on identifying patients at greatest risk using prediction scores. Objective: To identify the type of score that best predicts hospital readmissions. Design, Setting, and Participants: This prognostic study included 14 062 consecutive adult hospital patients with 16 649 discharges from a tertiary care center, suburban community hospital, and urban critical access hospital in Maryland from September 1, 2016, through December 31, 2016. Patients not included as eligible discharges by the Centers for Medicare & Medicaid Services or the Chesapeake Regional Information System for Our Patients were excluded. A machine learning rank score, the Baltimore score (B score) developed using a machine learning technique, for each individual hospital using data from the 2 years before September 1, 2016, was compared with standard readmission risk assessment scores to predict 30-day unplanned readmissions. Main Outcomes and Measures: The 30-day readmission rate evaluated using various readmission scores: B score, HOSPITAL score, modified LACE score, and Maxim/RightCare score. Results: Of the 10 732 patients (5605 [52.2%] male; mean [SD] age, 54.56 [22.42] years) deemed to be eligible for the study, 1422 were readmitted. The area under the receiver operating characteristic curve (AUROC) for individual rules was 0.63 (95% CI, 0.61-0.65) for the HOSPITAL score, which was significantly lower than the 0.66 for modified LACE score (95% CI, 0.64-0.68; P <.001). The B score machine learning score was significantly better than all other scores; 48 hours after admission, the AUROC of the B score was 0.72 (95% CI, 0.70-0.73), which increased to 0.78 (95% CI, 0.77-0.79) at discharge (all P <.001). At the hospital using Maxim/RightCare score, the AUROC was 0.63 (95% CI, 0.59-0.69) for HOSPITAL, 0.64 (95% CI, 0.61-0.68) for Maxim/RightCare, and 0.66 (95% CI, 0.62-0.69) for modified LACE score. The B score was 0.72 (95% CI, 0.69-0.75) 48 hours after admission and 0.81 (95% CI, 0.79-0.84) at discharge. In directly comparing the B score with the sensitivity at cutoff values for modified LACE, HOSPITAL, and Maxim/RightCare scores, the B score was able to identify the same number of readmitted patients while flagging 25.5% to 54.9% fewer patients. Conclusions and Relevance: Among 3 hospitals in different settings, an automated machine learning score better predicted readmissions than commonly used readmission scores. More efficiently targeting patients at higher risk of readmission may be the first step toward potentially preventing readmissions.
- Subjects
MARYLAND; ALGORITHMS; CONFIDENCE intervals; LONGITUDINAL method; MACHINE learning; NONPARAMETRIC statistics; HEALTH outcome assessment; RISK assessment; DATA analysis; RECEIVER operating characteristic curves; PATIENT readmissions; DATA analysis software; DESCRIPTIVE statistics; INDEPENDENT variables
- Publication
JAMA Network Open, 2019, Vol 2, Issue 3, pe190348
- ISSN
2574-3805
- Publication type
Article
- DOI
10.1001/jamanetworkopen.2019.0348